@@ -1508,6 +1508,7 @@ extern struct pid *cad_pid;
#define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */
#define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to,
* I am cleaning dirty pages from some other bdi. */
+#define __PF_MEMALLOC_NOLOCKDEP 0x00100000 /* All allocation requests will inherit __GFP_NOLOCKDEP */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
@@ -1519,6 +1520,12 @@ extern struct pid *cad_pid;
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
+#ifdef CONFIG_LOCKDEP
+#define PF_MEMALLOC_NOLOCKDEP __PF_MEMALLOC_NOLOCKDEP
+#else
+#define PF_MEMALLOC_NOLOCKDEP 0
+#endif
+
/*
* Only the _current_ task can read/write to tsk->flags, but other
* tasks can access tsk->flags in readonly mode for example
@@ -177,22 +177,27 @@ static inline bool in_vfork(struct task_struct *tsk)
* Applies per-task gfp context to the given allocation flags.
* PF_MEMALLOC_NOIO implies GFP_NOIO
* PF_MEMALLOC_NOFS implies GFP_NOFS
+ * PF_MEMALLOC_NOLOCKDEP implies __GFP_NOLOCKDEP
* PF_MEMALLOC_NOCMA implies no allocation from CMA region.
*/
static inline gfp_t current_gfp_context(gfp_t flags)
{
- if (unlikely(current->flags &
- (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+ unsigned int pflags = current->flags;
+
+ if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS |
+ PF_MEMALLOC_NOCMA | PF_MEMALLOC_NOLOCKDEP))) {
/*
* NOIO implies both NOIO and NOFS and it is a weaker context
* so always make sure it makes precedence
*/
- if (current->flags & PF_MEMALLOC_NOIO)
+ if (pflags & PF_MEMALLOC_NOIO)
flags &= ~(__GFP_IO | __GFP_FS);
- else if (current->flags & PF_MEMALLOC_NOFS)
+ else if (pflags & PF_MEMALLOC_NOFS)
flags &= ~__GFP_FS;
+ if (pflags & PF_MEMALLOC_NOLOCKDEP)
+ flags |= __GFP_NOLOCKDEP;
#ifdef CONFIG_CMA
- if (current->flags & PF_MEMALLOC_NOCMA)
+ if (pflags & PF_MEMALLOC_NOCMA)
flags &= ~__GFP_MOVABLE;
#endif
}
There are cases where calling kmalloc() can lead to false positive lockdep splat. One notable example that can happen in the freezing of the xfs filesystem is as follows: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(sb_internal); lock(fs_reclaim); lock(sb_internal); lock(fs_reclaim); *** DEADLOCK *** This is a false positive as all the dirty pages are flushed out before the filesystem can be frozen. However, there is no easy way to modify lockdep to handle this situation properly. One possible workaround is to disable lockdep by setting __GFP_NOLOCKDEP in the appropriate kmalloc() calls. However, it will be cumbersome to locate all the right kmalloc() calls to insert __GFP_NOLOCKDEP and it is easy to miss some especially when the code is updated in the future. Another alternative is to have a per-process global state that indicates the equivalent of __GFP_NOLOCKDEP without the need to set the gfp_t flag individually. To allow the latter case, a new PF_MEMALLOC_NOLOCKDEP per-process flag is now added. After adding this new bit, there are still 2 free bits left. Suggested-by: Dave Chinner <david@fromorbit.com> Signed-off-by: Waiman Long <longman@redhat.com> --- include/linux/sched.h | 7 +++++++ include/linux/sched/mm.h | 15 ++++++++++----- 2 files changed, 17 insertions(+), 5 deletions(-)